{"total":16,"rows":[{"id":"2306.09526","title":"Residual Q-Learning: Offline and Online Policy Customization without Value","created":"2023-06-15","cited_by_count":10,"area":"offlinerl"},{"id":"2502.12330","title":"X-IL: Exploring the Design Space of Imitation Learning Policies","created":"2025-02-17","cited_by_count":10,"area":"offlinerl"},{"id":"2212.02941","title":"Safe Imitation Learning of Nonlinear Model Predictive Control for Flexible Robots","created":"2022-12-06","cited_by_count":3,"area":"offlinerl"},{"id":"2402.16349","title":"C-GAIL: Stabilizing Generative Adversarial Imitation Learning with Control Theory","created":"2024-02-26","cited_by_count":3,"area":"offlinerl"},{"id":"2410.03847","title":"Enhancing Inverse Reinforcement Learning through Encoding Dynamic Information in Reward Shaping","created":"2024-10-04","cited_by_count":3,"area":"offlinerl"},{"id":"2406.03069","title":"\"Give Me an Example Like This\": Episodic Active Reinforcement Learning from Demonstrations","created":"2024-06-05","cited_by_count":2,"area":"offlinerl"},{"id":"2401.09332","title":"Synergistic Reinforcement and Imitation Learning for Vision-driven Autonomous Flight of UAV Along River","created":"2024-01-17","cited_by_count":1,"area":"offlinerl"},{"id":"2402.11367","title":"Multi Task Inverse Reinforcement Learning for Common Sense Reward","created":"2024-02-17","cited_by_count":1,"area":"offlinerl"},{"id":"2407.12113","title":"A Graph-based Adversarial Imitation Learning Framework for Reliable & Realtime Fleet Scheduling in Urban Air Mobility","created":"2024-07-16","cited_by_count":1,"area":"offlinerl"},{"id":"2510.00922","title":"On Discovering Algorithms for Adversarial Imitation Learning","created":"2025-10-01","cited_by_count":1,"area":"offlinerl"},{"id":"2304.07280","title":"Synthetically Generating Human-like Data for Sequential Decision Making Tasks via Reward-Shaped Imitation Learning","created":"2023-04-14","cited_by_count":0,"area":"offlinerl"},{"id":"2509.00574","title":"Learning Dolly-In Filming From Demonstration Using a Ground-Based Robot","created":"2025-08-30","cited_by_count":0,"area":"offlinerl"},{"id":"2510.16462","title":"Buzz, Choose, Forget: A Meta-Bandit Framework for Bee-Like Decision Making","created":"2025-10-18","cited_by_count":0,"area":"offlinerl"},{"id":"2512.08052","title":"An Introduction to Deep Reinforcement and Imitation Learning","created":"2025-12-08","cited_by_count":0,"area":"offlinerl"},{"id":"2603.02783","title":"Generative adversarial imitation learning for robot swarms: Learning from human demonstrations and trained policies","created":"2026-03-03","cited_by_count":0,"area":"offlinerl"},{"id":"2603.05440","title":"Latent Wasserstein Adversarial Imitation Learning","created":"2026-03-05","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}